inclusionAI/Duo-1.0-distill 发布：一个用于全双工交互的多模态世界模型
inclusionAI/Duo-1.0-distill
inclusionAI 发布 Duo-1.0-distill，一个用于实时音视频交互的全双工多模态世界模型，包含四步蒸馏的 Realization 权重，需与 causal-base 套件叠加使用。
Duo-1.0-distill
A Reciprocal World Model for Full-Duplex Interaction
Model Overview
Duo is a full-duplex multimodal world model for real-time audio-visual interaction. This repository contains the four-step distilled Realization weights for Duo 1.0.
| Field | Value |
|---|---|
| Version | Duo 1.0 |
| Variant | Four-step distilled Realization |
| Package | Realization overlay |
| Realization format | PyTorch Distributed Checkpoint (DCP) |
| Base dependency | inclusionAI/Duo-1.0-causal-base |
| Default sampler | Euler, 4 steps, flow shift 5.0 |
Usage
Download the complete Duo 1.0 causal-base bundle, then overlay these Realization weights into the same directory:
hf download inclusionAI/Duo-1.0-causal-base --local-dir weights
hf download inclusionAI/Duo-1.0-distill --local-dir weights
The shared Intent, codecs, speech models, and Realization backbone are supplied by the causal-base bundle. Runtime integrations can use realization/complete.json to identify the distilled model family.
For code, configuration, and runtime-specific integration instructions, see inclusionAI/Duo.
License
These weights were initialized from MiniMax H3 and subsequently trained by the Duo team. See LICENSE and NOTICE for the applicable terms.
来源: 蚂蚁 inclusionAI · Hugging Face 新模型 · huggingface.co